Search

Recently, the transformer-based model has shown superior performance in hyperspectral image classification (HSIC) due to its excellent ability to model long-term dependencies on sequence data. An important component of the transformer is the tokenizer, which can transform the features into semantic token sequences (STS). Nonetheless, transformer's semantic tokenization strategy is hardly representative of local relatively important high-level semantics because of its global receptive field. Recently, the Mamba-based methods have shown even stronger spatial context modeling ability than Transformer for HSIC. However, these Mamba-based methods mainly focus on spectral and spatial dimensions. They tend to extract semantic information in very long feature sequences or represent semantic information in several typical tokens, which may ignore some important semantics of the HSIs. In order to represent the semantic information of HSIs more holistically in Mamba, this article proposes a semantic tokenization-based Mamba (STMamba) model. In STMamba, a spectral-spatial feature extraction module is used to extract the spectral–spatial joint features. Then, a generated semantic token sequences module is designed to transform the features into STS. Subsequently, the STS are fed into the semantic token state spatial model to capture relationships between different semantic tokens. Finally, the fused semantic token is passed into a classifier for classification. Experimental results on three HSI datasets demonstrate that the proposed STMamba outperforms existing state-of-the-art deep learning and transformer-based methods.

While the current research has achieved satisfactory results for the registration of single mode data, there has always been a significant challenge in the registration of multi-modal images due to the obvious nonlinear radiation differences caused by different imaging mechanisms and imaging time. For example, multi-temporal visible, visible-synthetic aperture radar, visible-near infrared, near infrared-short wave infrared, visible-MAP, etc. To address this problem, we propose a Robust and Accurate Feature Matching Method for Multi-modal Geographic Images Spatial Registration (RAMMR) to fully extract common key points between images, weaken the radiation difference between data, and finally accurately match more inliers to realize multi-modal image registration. Considering the influence of noise and edge information on key point extraction, RAMMR first constructs a new scale space by introducing the Side Window Filter (SWF); Then, we improve Harris algorithm to extract key points based on the SWF scale space; After that, we propose an enhanced log-polar descriptor based on the gradient angles and gradient amplitudes of the scale space, which effectively improves the quality of the descriptor and avoids the mismatch of key points; Based on the standard Euclidean distance, we design a re-match strategy to obtain the initial matching results, and Random Sample Consensus (RANSAC) is used to eliminate outliers. Finally, the affine transformation parameters are calculated based on inliers, and multi-modal image registration is realized. RAMMR is evaluated on different multi-modal datasets and compared with some state-of-art methods. The experimental results show that RAMMR accurately registers multi-modal geographic images and obtains comparative results compared with benchmark methods. Our source datasets are publicly available at https://github.com/RSmfmr/multimodal-dataset.

Abstract Recently, transformer‐based networks have been introduced for the classification of hyperspectral image (HSI). Although transformer‐based methods can well capture spectral sequence information, their ability to fuse different types of information contained in HSI is still insufficient. To exploit rich spectral, spatial and semantic information in HSI, a novel semantic and spatial‐spectral feature fusion transformer (S3FFT) network is proposed in this study. In the proposed S3FFT method, spatial attention and efficient channel attention (ECA) modules are employed for the extraction of shallow spatial‐spectral features. Then, a transformer‐based module is designed to extract advanced fused features and to produce the pseudo‐label and class probability of each pixel for semantic feature extraction. Finally, the semantic, spatial and spectral features are combined by the transformer for classification. Compared with traditional deep learning methods and recently transformer‐based methods, the proposed S3FFT shows relatively better results on three HSI datasets.

Let $ G $ be a finite abelian group with exponent $ \exp(G) $ and $ S $ be a sequence with elements of $ G $. We say $ S $ is a zero-sum sequence if the sum of the elements in $ S $ is the zero element of $ G $. For a positive integer $ t $, let $ \mathtt{s}_{t\exp(G)}(G) $ (respectively, $ \mathtt{s}'_{t\exp(G)}(G) $) denote the smallest integer $ \ell $ such that every sequence (respectively, zero-sum sequence) $ S $ over $ G $ with $ |S|\geq \ell $ contains a zero-sum subsequence of length $ t\exp(G) $. The invariant $ \mathtt{s}_{t\exp(G)}(G) $ (respectively, $ \mathtt{s}'_{t\exp(G)}(G) $) is called the Generalized Erdős-Ginzburg-Ziv constant (respectively, Modified Erdős-Ginzburg-Ziv constant) of $ G $. In this paper, we discuss the relationship between Generalized Erdős-Ginzburg-Ziv constant and Modified Erdős-Ginzburg-Ziv constant, and determine $ \mathtt{s}'_{t\exp(G)}(G) $ for some finite abelian groups.

In recent years, deep neural networks have been widely used for hyperspectral image (HSI) classification and have shown excellent performance using numerous labeled samples. The acquisition of HSI labels is usually based on the field investigation, which is expensive and time consuming. Hence, the available labels are usually limited, which affects the efficiency of deep HSI classification methods. To improve the classification performance while reducing the labeling cost, this article proposes a semisupervised deep learning (DL) method for HSI classification, named pyramidal dilation attention convolutional network with active and self-paced learning (PDAC-ASPL), which integrates active learning (AL), self-paced learning (SPL), and DL into a unified framework. First, a densely connected pyramidal dilation attention convolutional network is trained with a limited number of labeled samples. Then, the most informative samples from the unlabeled set are selected by AL and queried real labels, and the highest confidence samples with corresponding pseudo labels are extracted by SPL. Finally, the samples from AL and SPL are added to the training set to retrain the network. Compared with some DL- and AL-based HSI classification methods, our PDAC-ASPL achieves better performance on four HSI datasets.

Phylogenetic analysis provides crucial insights into the evolutionary relationships and diversification patterns within specific taxonomic groups. In this study, we aimed to identify the phylogenetic relationships and explore the evolutionary history of Stipa using transcriptomic data. Samples of 12 Stipa species were collected from the Qinghai-Tibet Plateau and Mongolian Plateau, where they are widely distributed, and transcriptome sequencing was performed using their fresh spikelet tissues. Using bidirectional best BLAST analysis, we identified two sets of one-to-one orthologous genes shared between Brachypodium distachyon and the 12 Stipa species (9397 and 2300 sequences, respectively), as well as 62 single-copy orthologous genes. Concatenation methods were used to construct a robust phylogenetic tree for Stipa, and molecular dating was used to estimate divergence times. Our results indicated that Stipa originated during the Pliocene. In approximately 0.8 million years, it diverged into two major clades each consisting of native species from the Mongolian Plateau and the Qinghai-Tibet Plateau, respectively. The evolution of Stipa was closely associated with the development of northern grassland landscapes. Important external factors such as global cooling during the Pleistocene, changes in monsoonal circulation, and tectonic movements contributed to the diversification of Stipa. This study provided a highly supported phylogenetic framework for understanding the evolution of the Stipa genus in China and insights into its diversification patterns.

Multimodally distributed data is very common in remote sensing images, such as hyperspectral images (HSIs). It is important to capture the local manifold structure while preserving the global discriminant information in the multimodal data. In this article, an adaptive local discriminant analysis and distribution matching (ALDADM) method is designed for the domain adaptation (DA) in HSI classification. ALDADM uses adaptive local discriminant analysis to extract features that are discriminative and robust to multimodally distributed data. Meanwhile, considering the spectral properties of HSI, the domain shift is reduced by distribution matching and subspace alignment. During this learning process, ALDADM only selects density peak samples to reduce the influence of interfering samples. Four DA tasks are designing using University of Pavia, Center of Pavia, Yancheng, and Botswana HSI datasets. Compared with existing DA methods, the experimental results demonstrate that our ALDADM offers a superior performance.

Coastal wetlands mapping is a big challenge in remote sensing fields because of similar spectrum of different ground objects and their severe fragmentation and spatial heterogeneity. In this article, we propose a hyperspectral image transformer iN transformer (HSI-TNT) method for mapping coastal wetlands on ZiYuan1-02D (ZY1-02D) hyperspectral images, which uses two transformer deep networks to fuse local and global features. First, we put forward the idea that each hyperspectral pixel can be considered as a superpixel in spectral dimension, and subsequent position encodings are employed aiming to retain spatial information. After that, in each HSI-TNT block, the local information between pixels is extracted by inner T-Block, and added to the patch space by linear transformation to extract the global information by outer T-Block. Finally, the stacked HSI-TNT block, also known as HSI-TNT framework, is used for classification and mapping. Experimental results show that HSI-TNT achieves the best results on both Yancheng and Yellow River Delta wetlands data, with overall classification accuracy of 95.57% and 93.69%, respectively. The HSI-TNT combined with ZY1-02D satellite hyperspectral data has huge potentials in mapping coastal wetlands.

Traditional remote sensing (RS) image classification methods heavily rely on labeled samples for model training. When labeled samples are unavailable or labeled samples have different distributions from that of the samples to be classified, the classification model may fail. The cross-domain or cross-scene remote sensing image classification is developed for this case where an existing image for training and an unknown image from different scenes or domains for classification. The distribution inconsistency problem may be caused by the differences in acquisition environment conditions, acquisition scene, acquisition time, and/or changing sensors. To cope with the cross-domain remote sensing image classification problem, many domain adaptation (DA) techniques have been developed. In this article, we review DA methods in the fields of RS, especially hyperspectral image classification, and provide a survey of DA methods into traditional shallow DA methods (e.g., instance-based, feature-based, and classifier-based adaptations) and recently developed deep DA methods (e.g., discrepancy-based and adversarial-based adaptations).

Let $G$ be an additive finite abelian group with exponent $\exp(G)$ and $S$ be a sequence with elements of $G$. Let $\Sigma(S) \subset G$ denote the set of group elements which can be expressed as the sum of a nonempty subsequence of $S$. We say $S$ is zero-sum free if $0 \not\in \Sigma(S)$. In this paper, we determine the structures of the zero-sum free sequences $S$ such that $|S| = \exp(G)+2$ and $|\Sigma(S)| = 4\exp(G)-1$, which partly confirms a conjecture of J. Peng et al.

Recently, deep learning methods have been widely used in hyperspectral image (HSI) classification and achieved good performance. However, the performance of these methods may be limited because of the scarcity of labeled samples in HSI data. To solve the small-sample classification problem, a deep contrastive learning network (DCLN) method is proposed in this paper. The proposed DCLN method first constructs contrastive groups and trains the network through contrastive learning. Then, it uses the trained network to extract spectral–spatial features of HSI pixels and generates pseudo-label for each unlabeled sample based on the spatial–spectral mixing distance. Finally, the pseudo-labeled samples with higher confidence are selected and added to the original training set to retrain the network. By gradually increasing pseudo-labeled samples and refining the contrastive learning network, the model shows good feature learning ability and classification performance with the limited labeled samples. Experimental results on 4 public HSI datasets demonstrate that the proposed DCLN method can achieve better performance than existing state-of-the-art methods.

Let $ F $ be a finite field of characteristic $ p $ having $ q = p^n $ elements and $ G $ be an abelian group. In this paper, we determine the structure of the group of units of the group algebra $ FG $, where $ G $ is an abelian group of order $ 17\leq |G|\leq 20 $.

Hyperspectral imageclassification is one of the most important steps in HSI analysis and challenging task for hyperspectral data processing, hyperspectral image contains rich spatial and spectral information. The abundance of spectral and spatial information is helpful to improve the classification accuracy. In this article, we propose a spectral-spatial random patches network (SSRPNet), which directly regards the random patches taken from the image as the convolution kernels without any training. The spectral-spatial feature extracted by SSRPNet stacked into a high dimensional vector, which combined with shallow, deep, spectral, spatial feature. Then, the high dimensional vector is fed into graph-based learning methods for classification, which can achieve excellent classification performance by randomly selecting a subset of features from a small sample point to create a graph. Experimental results on three datasets show that the proposed method can achieve satisfactory classification results compared with closely related methods.

Deep learning (DL) algorithms have been demonstrated to have great potential in hyperspectral image (HSI) classification. However, most DL methods mainly focus on improving classification performance, neglecting the computational cost. In order to broaden the application scenarios of DL-based HSI classification methods, it is necessary to develop lightweight and fast models to fit the deployment needs of computational-resource-limited platforms. Taking into account the efficiency and accuracy, this article designs a lightweight network architecture based on spectral and channel-wise attention modules, namely LiteSCANet, for HSI classification. It contains a residual double-branch structure, which makes the model effectively extract spectral-spatial features and achieve good performance with fast inference speed and low computational consumption (i.e., floating-point operations, number of parameters, and graphics processing unit memory usage). The experiment results on four benchmark datasets show that our proposed model achieves an excellent trade-off between efficiency and accuracy compared with the other six existing networks.

This article presents a label similarity probability filter (LSPF) to make hyperspectral image postclassification. The LSPF is inspired by the first law of geography and proposes a class label probability function to quantify the probability of both centered and its neighboring pixels belonging to the same class. It first classifies the hyperspectral data using the regular support vector machine classifier. Then, it binarizes the posterior classification result to obtain the binary label maps of each class. After that, it traverses all spatial windows centered by each pixel and calculates the cumulative probability of all pixels in each class. Finally, the cumulative probabilities are used to make reclassification to obtain the refined classification map. The experiments on Indian Pines, Pavia University, and ZY1-02D Yellow River Estuary data show that LSPF greatly improves the classification accuracy of spectral signatures and outperforms other state-of-the-art spectral–spatial methods.

Recent studies in cross-domain classification have shown that discriminant information of both source and target domains is very important. In this article, we propose a new domain adaptation (DA) method for hyperspectral image (HSI) classification, called graph embedding and distribution alignment (GEDA). GEDA uses the graph embedding method and a pseudo-label learning method to learn interclass and intraclass divergence matrices of source and target domains, which preserves the local discriminant information of both domains. Meanwhile, spatial and spectral features of HSI are used, and distribution alignment and subspace alignment are performed to minimize the spectral differences between domains. We perform DA tasks on Yancheng, Botswana, University of Pavia, and Center of Pavia, Shanghai and Hangzhou data sets. Experimental results show that the classification performance of the proposed GEDA is better than that of existing DA methods.

Owing to the complicated and heterogeneous distribution characteristics of wetland features, the existing hyperspectral technology is difficult to investigate the inner-pixel subtle changes. In this article, we present a subpixel change detection method based on collaborative coupled unmixing (SCDUM) for monitoring coastal wetlands. A novel multitemporal and spatial scale collaborative endmember extraction method based on joint spatial and spectral information is proposed. In the proposed method, the multitemporal hyperspectral images are first jointly clustered and segmented based on multifeature fusion of spectral features, texture features, and shape features. Then, a different spatial scale nonnegative matrix factorization based on original and downsampled multitemporal hyperspectral images is proposed to accurately extract the pure endmembers of each segmented images. Finally, the global abundance of the multitemporal image is effectively estimated for change detection. In addition, in order to verify the accuracy of the change detection results without reference, an accuracy verification strategy by using high spatial resolution Sentinel-2A image as auxiliary data is implemented. The Yellow River Estuary coastal wetland was selected as the research area, and the Gaofen-5 and ZY-1 02D hyperspectral images were used as the research data. In particular, the proposed method not only provides the overall change information, but also obtains the component of change direction and intensity of each kind of endmember, and the experimental results show that the SCDUM gives more accurate detection results, with closer to the endmember spectral curves of real objects, compared with other state-of-the-art methods.

Abstract Background Plant transcription factors (TFs) are key transcriptional regulators to manipulate the regulatory network of host immunity. However, the globally transcriptional reprogramming of plant TF families in response to pathogens, especially between the resistant and susceptible host plants, remains largely unknown. Results Here, we performed time-series RNA-seq from a resistant pepper line CM334 and a susceptible pepper line EC01 upon challenged with Phytophthora capsici, and enrichment analysis indicated that WRKY family most significantly enriched in both CM334 and EC01. Interestingly, we found that nearly half of the WRKY family members were significantly up-regulated, whereas none of them were down-regulated in the two lines. These induced WRKY genes were greatly overlapped between CM334 and EC01. More strikingly, most of these induced WRKY genes were expressed in time-order patterns, and could be mainly divided into three subgroups: early response (3 h-up), mid response (24 h-up) and mid-late response (ML-up) genes. Moreover, it was found that the responses of these ML-up genes were several hours delayed in EC01. Furthermore, a total of 19 induced WRKY genes were selected for functional identification by virus-induced gene silencing. The result revealed that silencing of CaWRKY03–6, CaWRKY03–7, CaWRKY06–5 or CaWRKY10–4 significantly increase the susceptibility to P. capsici both in CM334 and EC01, indicating that they might contribute to pepper’s basal defense against P. capsici; while silencing of CaWRKY08–4 and CaWRKY01–10 significantly impaired the disease resistance in CM334 but not in EC01, suggesting that these two WRKY genes are prominent modulators specifically in the resistant pepper plants. Conclusions These results considerably extend our understanding of WRKY gene family in pepper’s resistance against P. capsici and provide potential applications for genetic improvement against phytophthora blight.

Solar flares are solar storm events driven by the magnetic field in the solar activity area. Solar flare, often associated with solar proton event or CME, has a negative impact on ratio communication, aviation, and aerospace. Therefore, its forecasting has attracted much attention from the academic community. Due to the limitation of the unbalanced distribution of the observation data, most techniques failed to effectively learn complex magnetic field characteristics, leading to poor forecasting performance. Through the statistical analysis of solar flare magnetic map data observed by SDO/HMI from 2010 to 2019, we find that unsupervised clustering algorithms have high accuracy in identifying the sunspot group in which the positive samples account for the majority. Furthermore, for these identified sunspot groups, the ensemble model that integrates the capability of boosting and convolutional neural network (CNN) achieves high-precision prediction of whether the solar flares will occur in the next 48 hours. Based on the above findings, a two-stage solar flare early warning system is established in this paper. The F1 score of our method is 0.5639, which shows that it is superior to the traditional methods such as logistic regression and support vector machine (SVM).

This paper proposes a simple and effective spatial-spectral (SESS) method for mapping large-scale coastal wetlands using China ZY1-02D satellite hyperspectral data. First, the improved sparse subspace clustering algorithm is implemented to select presentative bands, and then the multi-scale low-rank decomposition algorithm is employed to extract multi-scale spatial features. After that, the extracted spatial and selected spectral features are stacked and fused using presented Landmark-neighborhood preserving embedding algorithm. Finally, the low-dimensional fused features are classified with two popular classifiers (i.e., random forest and support vector machine) to map coastal wetlands. Experiments results show that the SESS obtains the highest classification accuracy of 96.92% and 94.84% on Yellow River Delta and Yancheng coastal wetlands of China, respectively, exhibiting good capability in accurately identifying complicated ground objects. This paper is the first attempt to investigate the potentials of China ZY1-02D satellite hyperspectral data, and the SESS can also be applied into other hyperspectral data.

This article proposes a novel unsupervised domain adaptation (DA) method called ideal regularized discriminative multiple kernel subspace alignment (IRDMKSA) for hyperspectral image (HSI) classification. The proposed IRDMKSA method includes three main steps: ideal regularization, discriminative multiple kernel learning, and subspace alignment. The ideal regularization strategy exploits label information of source domain to refine the standard source and target kernels and also to build a connection between them. The discriminative multiple kernel learning can learn a composite kernel to describe the nonlinearity of HSI samples by fusing complementary information among different single kernels. Finally, the subspace alignment is used to diminish the difference between source and target composite kernels. The proposed IRDMKSA method exploits both the sample similarity and label similarity and makes the resulting kernel more appropriate for DA tasks. Experimental results on four DA tasks show that the performance of IRDMKSA is better than some classical unsupervised DA methods for the HSI classification.

Hyperspectral image (HSI) classification is one of the hot research topics in the field of remote sensing. The performance of HSI classification greatly depends on the effectiveness of feature learning or feature design. Traditional vector-based spectral–spatial features have shown good performance in HSI classification. However, when the number of labeled samples is limited, the performance of these vector-based features is degraded. To fully mine the discriminative features in small-sample case, a novel local matrix feature (LMF) was designed to reflect both the correlation between spectral pixels and the spectral bands in a local spatial neighborhood. In particular, the LMF is a linear combination of a local covariance matrix feature and a local correntropy matrix feature, where the former describes the correlation between spectral pixels and the latter measures the similarity between spectral bands. Based on the constructed LMFs, a simple Log-Euclidean distance-based linear kernel is introduced to measure the similarity between them, and an LMF-based kernel joint sparse representation (LMFKJSR) model is proposed for HSI classification. Due to the superior performance of region covariance and correntropy descriptors, the proposed LMFKJSR shows better results than existing vector-feature-based and matrix-feature-based support vector machine (SVM) and JSR methods on three well-known HSI data sets in the case of limited labeled samples.

The hyperspectral, multispectral, and synthetic aperture radar (SAR) remote sensing images provide complementary advantages in high spectral resolution, high spatial resolution, and geometric and polarimetric properties, generally. How to effectively integrate cross-modal information to obtain a high spatial resolution hyperspectral image with the characteristics of the SAR is promising. However, due to divergent imaging mechanisms of modalities, existing SAR and optical image fusion techniques generally remain limited due to the spectral or spatial distortions, especially for complex surface features such as coastal wetlands. This paper provides, for the first time, an efficient multi-resolution collaborative fusion method for multispectral, hyperspectral, and SAR images. We improve generic multi-resolution analysis with spectral-spatial weighted modulation and spectral compensation to achieve minimal spectral loss. The backscattering gradients of SAR are guided to fuse, which is calculated from saliency gradients with edge preserving. The experiments were performed on ZiYuan-1 02D (ZY-1 02D) and GaoFen-5B (AHSI) hyperspectral, Sentinel-2 and GaoFen-5B (VIMI) multispectral, and Sentinel-1 SAR images in the challenging coastal wetlands. Specifically, the fusion results were comprehensively tested and verified on the qualitative, quantitative, and classification metrics. The experimental results show the competitive performance of the proposed method.

Schizochytrium sp. is the best natural resource for omega-3 long-chain polyunsaturated fatty acids. We report a high-quality genome sequence of Schizochytrium limacinum SR21, which has a 63 Mb genome size, with a contig N50 of 2.67 Mb and 6,838 protein-coding genes. Phylogenomic and comparative genomic analyses revealed that DHA-producing Schizochytrium and Aurantiochytrium strains were highly similar and possessed similar genes. Analysis of the fatty acid synthase (FAS) for LC-PUFAs production results in the annotation of all genes in map00062 and map01212. A gene cluster and 10 ORFs related to PKS pathway were found in the genome. 1,402 differentially expressed genes (DEGs) of the treated groups (0.5 g/L yeast extract) were identified by comparing with the control groups (1.0 g/L yeast extract) at 36 h. A weighted gene coexpression network analysis revealed that 2 of 7 modules correlated highly with the fatty acid and DHA contents. The DEGs and transcription factors were significantly correlated with fatty acid biosynthesis, including MYB, Zinc Finger and ACOX. The results showed that these hub genes are regulated by genes involved in fatty acid biosynthesis pathways. The results providing an important reference for further research on promoting fatty acid and DHA accumulation in S. limacinum SR21.

Hyperspectral unmixing (HU) is a research hotspot of hyperspectral remote sensing technology. As a classical HU method, the nonnegative matrix factorization (NMF) unmixing method can decompose an observed hyperspectral data matrix into the product of two nonnegative matrices, i.e., endmember and abundance matrices. Because the objective function of NMF is the traditional least-squares function, NMF is sensitive to noise. In order to improve the robustness of NMF, this paper proposes a maximum likelihood estimation (MLE) based NMF model (MLENMF) for unmixing of hyperspectral images (HSIs), which substitutes the least-squares objective function in traditional NMF by a robust MLE-based loss function. Experimental results on a simulated and two widely used real hyperspectral data sets demonstrate the superiority of our MLENMF over existing NMF methods.

Known as input in the Numerical Weather Prediction (NWP) models, Microwave Radiation Imager (MWRI) data have been widely distributed to the user community. With the development of remote sensing technology, improving the geolocation accuracy of MWRI data are required and the first step is to estimate the geolocation error accurately. However, the traditional method, such as the coastline inflection method (CIM), usually has the disadvantages of low accuracy and poor anti-noise ability. To overcome these limitations, this paper proposes a novel ℓ p iterative closest point coastline inflection method ( ℓ p -ICP CIM). It assumes that the field of views (FOVs) across the coastline can degenerate into a step function and employs an ℓ p ( 0 ≤ p < 1 ) sparse regularization optimization model to solve the coastline point. After estimating the coastline points, the ICP algorithm is employed to estimate the corresponding relationship between the estimated coastline points and the real coastline. Finally, the geolocation error can be defined as the distance between the estimated coastline point and the corresponding point on the true coastline. Experimental results on simulated and real data sets show the effectiveness of our method over CIM. The accuracy of the geolocation error estimated by ℓ p -ICP CIM is up to 0.1 pixel, in more than 90 % of cases. We also show that the distribution of brightness temperature near the coastline is more consistent with the real coastline and the average geolocation error is reduced by 63 % after geolocation error correction.

By means of joint sparse representation (JSR) and kernel representation, kernel joint sparse representation (KJSR) models can effectively model the intrinsic nonlinear relations of hyperspectral data and better exploit spatial neighborhood structure to improve the classification performance of hyperspectral images. However, due to the presence of noisy or inhomogeneous pixels around the central testing pixel in the spatial domain, the performance of KJSR is greatly affected. Motivated by the idea of self-paced learning (SPL), this paper proposes a self-paced KJSR (SPKJSR) model to adaptively learn weights and sparse coefficient vectors for different neighboring pixels in the kernel-based feature space. SPL strateges can learn a weight to indicate the difficulty of feature pixels within a spatial neighborhood. By assigning small weights for unimportant or complex pixels, the negative effect of inhomogeneous or noisy neighboring pixels can be suppressed. Hence, SPKJSR is usually much more robust. Experimental results on Indian Pines and Salinas hyperspectral data sets demonstrate that SPKJSR is much more effective than traditional JSR and KJSR models.

Jointly using spectral and spatial information has become a mainstream strategy in the field of hyperspectral image (HSI) processing, especially for classification. However, due to the existence of noisy or correlated spectral bands in the spectral domain and inhomogeneous pixels in the spatial neighborhood, HSI classification results are often degraded and unsatisfactory. Motivated by the attention mechanism, this paper proposes a spatial–spectral squeeze-and-excitation (SSSE) module to adaptively learn the weights for different spectral bands and for different neighboring pixels. The SSSE structure can suppress or motivate features at a certain position, which can effectively resist noise interference and improve the classification results. Furthermore, we embed several SSSE modules into a residual network architecture and generate an SSSE-based residual network (SSSERN) model for HSI classification. The proposed SSSERN method is compared with several existing deep learning networks on two benchmark hyperspectral data sets. Experimental results demonstrate the effectiveness of our proposed network.

A new method of superpixel segmentation-based local pixel neighborhood preserving embedding (SSLPNPE) is proposed for the fusion of hyperspectral and light detection and ranging (LiDAR) data based on the extinction profiles (EPs), superpixel segmentation and local pixel neighborhood preserving embedding (LPNPE). A new workflow is proposed to calibrate the Goddard’s LiDAR, hyperspectral and thermal (G-LiHT) data, which allows our method to be applied to actual data. Specifically, EP features are extracted from both sources. Then, the derived features of each source are fused by the SSLPNPE. Using the labeled samples, the final label assignment is produced by a classifier. For the open standard experimental data and the actual data, experimental results prove that the proposed method is fast and effective in hyperspectral and LiDAR data fusion.